AI Paper Atlas

Research map / Detection and segmentation / CNN features

Salient Object Ranking With Position-Preserved Attention

Hao Fang, Daoxin Zhang, Yi Zhang, Minghao Chen, Jiawei Li, Yao Hu, Deng Cai, Xiaofei He

ICCV 2021 · Detection and segmentation › CNN features · approach: RGB salient object detection · 30 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train end-to-end instead of two-stage (ablation)PPA SOR network · ASR datasetSOR: 0.835 -> 0.841Improved
train end-to-end instead of two-stage (ablation)PPA SOR network · ASR datasetMAE (lower is better): 0.082 -> 0.081Improved
add position embedding stage to baseline SOR branch (ablation)Baseline SOR branch · ASR datasetMAE (lower is better): 0.104 -> 0.095Improved
add position embedding stage to baseline SOR branch (ablation)Baseline SOR branch · ASR datasetSOR: 0.830 -> 0.836Improved
add feature interaction (Transformer attention) stage to baseline (ablation)Baseline SOR branch · ASR datasetMAE (lower is better): 0.104 -> 0.088Improved
add feature interaction (Transformer attention) stage to baseline (ablation)Baseline SOR branch · ASR datasetSOR: 0.830 -> 0.839Improved
add both position embedding and attention to baseline (ablation)Baseline SOR branch · ASR datasetMAE (lower is better): 0.104 -> 0.081Improved
add attention on top of position embedding (ablation)Baseline+pos · ASR datasetSOR: 0.836 -> 0.841Improved
use PPA position embedding instead of concatenated center coordinates (ablation)SOR branch · ASR datasetMAE (lower is better): 0.092 -> 0.081Improved
add scale (w, h) to concatenated position information (ablation)SOR branch with C_x,C_y · ASR datasetMAE (lower is better): 0.092 -> 0.088Improved
use learnable look-up position embedding instead of PPA coordinate maps (ablation)SOR branch · ASR datasetSOR: 0.841 -> 0.821Hurt
add scale to learnable position embedding (ablation)Learnable pos · ASR datasetSOR: 0.821 -> 0.834Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy